© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4613
    Prev
    Next
    INDEX
    Explanations

    the presence of formatting or punctuation details in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    185
    +0.10
    0.5%
    405
    +0.10
    0.4%
    666
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    544
    +0.10
    0.02
    514
    +0.09
    0.02
    Negative Logits
    ufact
    -0.89
    aceae
    -0.78
    ktop
    -0.76
    ancies
    -0.66
    ospace
    -0.65
    estones
    -0.65
    icular
    -0.64
    rette
    -0.64
    ById
    -0.64
    ement
    -0.62
    POSITIVE LOGITS
    é¾įå
    0.74
    UFF
    0.73
    RA
    0.69
    SL
    0.68
    AF
    0.67
    AIN
    0.67
    quickShipAvailable
    0.67
    REP
    0.66
    ORE
    0.66
    442
    0.66
    Activations Density 0.076%

    No Known Activations